Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling

Abstract

Phenotype imputation plays a crucial role in improving comprehensive and accurate medical evaluation, which in turn can optimize patient treatment and bolster the reliability of clinical research. Despite the adoption of various techniques, multi-modal biological data, which can provide crucial insights into a patient’s overall health, is often overlooked. With multi-modal biological data, patient characterization can be enriched from two distinct views: the biological view and the phenotype view. However, the heterogeneity and imprecise nature of the multi-modal data still pose challenges in developing an effective method to model from two views. In this paper, we propose a novel framework to incorporate multi-modal biological data via view decoupling. Specifically, we segregate the modeling of biological data from phenotype data in a graph-based learning framework. From the biological view, the latent factors in biological data are discovered to model patient correlation. From the phenotype view, phenotype co-occurrence can be modeled to reveal patterns across patients. Hence, patients are encoded from these two distinct views. To mitigate the influence of noise and irrelevant information in biological data, we devise the cross-view contrastive knowledge distillation that distills insights from the biological view to enhance phenotype imputation. Phenotype imputation with the proposed model demonstrates superior performance over state-of-the-art models on the real-world biomedical database.